@techreport{kim-nmlrg-network-00,
    number =    {draft-kim-nmlrg-network-00},
    type =      {Internet-Draft},
    institution =   {Internet Engineering Task Force},
    publisher = {Internet Engineering Task Force},
    note =      {Work in Progress},
    url =       {https://datatracker.ietf.org/doc/draft-kim-nmlrg-network/00/},
    author =    {Min-Suk Kim and Yong-Geun Hong},
    title =     {{Collaborative Intelligent Multi-agent Reinforcement Learning over a Network}},
    pagetotal = 12,
    year =      2017,
    month =     mar,
    day =       13,
    abstract =  {This document describes agent reinforcement learning (RL) in a distributed environment to transfer or share information for autonomous shortest path-planning over a communication network. The centralized node, which is the main node to manage agent workflow in hybrid peer-to-peer environment, provides a cumulative reward for each action that a given agent takes with respect to an optimal path based on a to-be-learned policy over the learning process. A reward from the centralized node is reflected when an agent explores to reach its destination for autonomous shortest path-planning in distributed nodes.},
}